FLUX 3 · First & Last Frame to Video
FLUX 3 is Black Forest Labs' video model that builds the motion between two keyframes. Upload a start and end image for an HD clip up to 20 seconds.
first last frame
flux 3
flux 3 video
image to video
0
96
Nodes & Models
Flux3FirstLastFrameToVideo_floyo
VideoToFrames
LoadImage
CreateVideo
SaveVideo
FloyoStickyNote
ABOUT THE WORKFLOW
Motion between two frames
Upload a start image and an end image, and the model builds the motion between them into an HD clip up to 20 seconds. A prompt is optional. Add one to steer the motion, or leave it empty and the model works out the transition on its own.
Partner node. This workflow calls an external API, so each run uses credits from your API wallet. No API key needed. Floyo handles the connection.
Model
FLUX 3 by Black Forest Labs. The lab's first multimodal video model, trained jointly on images, video, and audio in one architecture. In first-and-last-frame mode, it generates a controlled transition between two keyframes as an HD or Full HD clip up to 20 seconds, with lip-synced dialogue in more than 14 languages.
HOW IT WORKS
Step 1. Upload your start image
The first frame of the clip. It sets the subject, scene, and look.
Works great with: portraits · products · scenes · matching pairs
Step 2. Upload your end image
The last frame. The model works out the motion from the first image to this one.
Step 3. Describe the motion (optional)
Add a prompt to steer the camera or action, or leave it empty to let the model decide.
Step 4. Hit run and download
The model builds the transition in one pass and saves the clip. The file saved here is picture only, even though the model generates audio.
Ready for: editing timelines · social · ads
First time? Leave every setting as-is. The defaults (auto ratio · 720p · 5 seconds) are the right starting point for almost everyone.
RECOMMENDED SETTINGS
Quick-start guide. Find the goal that matches yours and copy the settings.
Standard use (most people) — auto aspect ratio, 720p, 5 seconds. The right starting point for almost everyone.
Making vertical content — set the aspect ratio to 9:16 for phones and short-form feeds. Auto matches your input images.
Want higher quality — switch the resolution to Full HD. It sharpens the clip and costs more per second.
Want a longer transition — raise the duration up to the 20-second maximum. Anything past 20 seconds needs a continuation step.
Keeping cost down — lower the duration and the resolution, since both drive the per-run cost. A 20-second Full HD clip costs much more than a 5-second HD one.
The result crops or morphs — use two images with a similar aspect ratio and a shared subject and setting. Unrelated images morph instead of moving cleanly.
Prompt: The prompt is optional here, since the two keyframes define most of the motion. When you do add one, describe the camera or action between the frames, like "slow push in as she turns her head." The cleanest results come from a start and end image that share a subject and setting.
LEARN
📹 Videos
ComfyUI 101 Free Course ft. Sebastian Kamph
Floyo 101 for Team Collaboration
✨ Quick links
USE CASES
🔄 Smooth Transitions
Turn two stills into a clean transition, like a before and after.
🎬 Controlled Motion
Set the exact start and end of a shot and let the model fill the middle.
📦 Product Reveals
Move from a closed to an open state, or one angle to another, in a single clip.
📱 Social & Short-form
Make quick vertical transitions from a matched pair of images.
WHAT WORKS BEST / WHAT TO AVOID
✅ Works great
Two images that share a subject and setting
A start and end with a similar aspect ratio
A clear change to move between
Clips of 20 seconds or less
⚠️ May produce softer results
Unrelated start and end images
Images with mismatched aspect ratios
Clips pushed past 20 seconds in one run
A transition with no clear path between frames
FAQ
What is FLUX 3?
FLUX 3 is Black Forest Labs' first multimodal video model, announced in July 2026 and made generally available in August 2026. It is trained jointly on images, video, and audio, and generates HD video up to 20 seconds. This workflow runs it in first-and-last-frame mode, building the motion between two keyframes you upload.
How does first and last frame to video work?
You upload a start image and an end image, and the model generates the motion that connects them, using the first as the opening frame and the second as the closing frame. A prompt is optional and only steers the motion in between. The transition is cleanest when the two images share a subject and setting.
Does the saved video have sound?
No. FLUX 3 generates native audio alongside the picture, but this workflow saves the clip as picture only, because it rebuilds the video into frames without the sound track. You get a silent HD clip, so plan to add or replace audio in your editor if you need it.
Do the two images need to match?
They work best when they share a similar aspect ratio and a common subject and setting. Mismatched aspect ratios can crop the result, and two unrelated images tend to morph into each other rather than move cleanly, so a matched pair gives the most controlled transition.
How long can a FLUX 3 clip be?
A single generation runs up to 20 seconds, which is longer than the roughly 10-second ceiling on many video models. Clips are HD by default, with Full HD available, and anything longer than 20 seconds needs a continuation step rather than one pass.
Can I use FLUX 3 videos commercially?
FLUX 3 is a proprietary model accessed through Black Forest Labs' API, so commercial use is governed by BFL's terms and its pay-as-you-go pricing rather than an open license. Commercial use is generally supported for ads and content, but review BFL's current terms and make sure you have the rights to the images you upload.
How to run FLUX 3 online?
You can run FLUX 3 online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, upload a start and end image, and hit run. Free to try.
WHY FLOYO?
Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.
A creator builds a transition and likes the result. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.
For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.
Ready to try it?
Upload a start and an end image, then run it.
Questions? Watch the free course or check the FAQ above.
Read more



